© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    digits and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åį«è§Ĩ
    -0.21
     inh
    -0.20
    ëį°
    -0.19
    yı
    -0.19
     Anch
    -0.18
    bero
    -0.18
    ÑĢеги
    -0.18
     Caucus
    -0.18
    sam
    -0.18
    lest
    -0.18
    POSITIVE LOGITS
    ally
    0.32
    ically
    0.26
    als
    0.24
    ical
    0.23
    ials
    0.23
    oidal
    0.23
    ied
    0.22
    ress
    0.22
    ential
    0.22
    rees
    0.22
    Activations Density 0.013%

    No Known Activations